Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication - Volume 14, Issue 1, 2008

This article describes the implementation and evaluation of WWW2REL, a domain-independent and pattern-based knowledge discovery system which extracts semantic relation instances from text fragments on the WWW so as to assist terminologists updating or expanding existing ontologies. Unlike most comparable systems, WWW2REL is special in that it can be applied to any semantic relation type and operates directly on unannotated and uncategorized WWW text snippets rather than static repositories of academic papers from the target domain. The WWW is used for knowledge pattern (KP) discovery, KP filtering and relation instance discovery. The system is tested with the help of the biomedical UMLS Metathesaurus for four different relation types and is manually evaluated by four domain experts. This system evaluation shows how ranking relation instances by a measure of “knowledge pattern range” and applying two heuristics yields an average performance of 70% to 65% of the maximum possible F-score by top 10 and top 50 instances, respectively. Importantly, results show that much valuable information not present in the UMLS can be found through the proposed method. Finally, the article examines the domain-dependence of different aspects of the pattern-based knowledge discovery approach proposed.

Pattern-based approaches for knowledge identification in texts assume that linguistic regularities always characterise the same kind of knowledge, such as semantic relations. In this paper, we report the experimental evaluation of a large set of patterns using an ontology enrichment tool: Caméléon. Results emphasize the strong influence of the corpus on pattern efficiency and on their meaning. This influence confirms two of the hypotheses that motivated to define Caméléon as a support used in a human-driven process: (1) patterns and relations must be adapted to each project; (2) human interpretation is required to decide how to report the pieces of knowledge identified with patterns in the ontology.

In this paper we present a description of the role of definitional verbal patterns for the extraction of semantic relations. Several studies show that semantic relations can be extracted from analytic definitions contained in machine-readable dictionaries (MRDs). In addition, definitions found in specialised texts are a good starting point to search for different types of definitions where other semantic relations occur. The extraction of definitional knowledge from specialised corpora represents another interesting approach for the extraction of semantic relations. Here, we present a descriptive analysis of definitional verbal patterns in Spanish and the first steps towards the development of a system for the automatic extraction of definitional knowledge.

This paper presents a catalogue of lexical patterns in Spanish for extracting semi-automatically concepts linked by the part-whole relation in the ceramics subject area. These lexical patterns have been obtained from the analysis of a corpus of texts about ceramics in which the linguistic structures linking terms related by the part-whole relation have been identified. These linguistic structures have been classified and their canonical form has been obtained in order to create pattern candidates. Finally, the precision of these patterns has been measured.

In the widely bi- and multilingual context of work in terminology and terminography today, and with the increasing volume of text-based resources available for carrying out this work, there is a need for computer tools to assist terminologists and terminographers in their tasks — including knowledge acquisition, conceptual description, creation of concept systems, formulation of definitions, and establishment of equivalence between terms — in two or more languages. Conceptual relations may be very useful for all of these applications. One method of semi-automatically locating information about conceptual relations uses knowledge patterns, i.e., linguistic markers of relations that can be used to find segments of text that convey this information. However, this kind of approach faces a number of serious challenges, including that of evaluating the certainty and thus ultimate usefulness of the information identified. Moreover, to date little research has been carried out to evaluate whether knowledge-pattern-based approaches may be expected to encounter comparable phenomena with similar frequency in different languages. This article will explore expressions of uncertainty observed in occurrences of English and French knowledge patterns identifying conceptual relations of ASSOCIATION and CAUSE–EFFECT, and how these may differ in the two languages.